Train NN with new data while maintaining previous training
显示 更早的评论
Hey, After training a network with a large set of data, I want to "adjust" the training with new small incoming data - without resting the weights and biases.
Basically I want to continue the training for every new data to enhance the network - but not to run an entire new NN learning with the old +new data
How can I do that?
采纳的回答
Ameer Hamza
2018-5-27
0 个投票
You are trying to do transfer learning. This is not only possible but quite popular techniques nowadays. Refer to this example to get the idea how to do it in MATLAB.
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
产品
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
